unimore/bda-6-steffo
unimore/bda-6-steffo
1
Fork 0
mirror of https://github.com/Steffo99/unimore-bda-6.git synced 2024-11-21 23:44:19 +00:00
Code Activity

Fix some leftover bugs

Browse source
This commit is contained in:
Steffo 2023-02-10 05:18:24 +01:00
parent 3d9eeecb2a
commit 4f40aa44b4
Signed by: steffo
GPG key ID: 2A24051445686895
3 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
unimore_bda_6/__main__.py
View file

@ -39,19 +39,19 @@ def main():
slog.debug("Selected sample_func: %s", sample_func.__name__) slog.debug("Selected sample_func: %s", sample_func.__name__)
for SentimentAnalyzer in [ for SentimentAnalyzer in [
NLTKSentimentAnalyzer,
TensorflowCategorySentimentAnalyzer, TensorflowCategorySentimentAnalyzer,
NLTKSentimentAnalyzer,
]: ]:
slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}") slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}")
slog.debug("Selected SentimentAnalyzer: %s", SentimentAnalyzer.__name__) slog.debug("Selected SentimentAnalyzer: %s", SentimentAnalyzer.__name__)
for Tokenizer in [ for Tokenizer in [
PottsTokenizer,
PottsTokenizerWithNegation,
PlainTokenizer, PlainTokenizer,
LowercaseTokenizer, LowercaseTokenizer,
NLTKWordTokenizer, NLTKWordTokenizer,
PottsTokenizer,
PottsTokenizerWithNegation,
]: ]:
slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}.{Tokenizer.__name__}") slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}.{Tokenizer.__name__}")

2
unimore_bda_6/analysis/nltk_sentiment.py
View file

@ -40,7 +40,7 @@ class NLTKSentimentAnalyzer(BaseSentimentAnalyzer):
Convert the `Text` of a `DataTuple` to a `TokenBag`. Convert the `Text` of a `DataTuple` to a `TokenBag`.
""" """
count_passage(log, "tokenize_datatuple", 100) count_passage(log, "tokenize_datatuple", 100)
return self.tokenizer.tokenize_plain(datatuple.text), datatuple.category return self.tokenizer.tokenize_and_split_plain(datatuple.text), datatuple.category
def _add_feature_unigrams(self, dataset: t.Iterator[tuple[TokenBag, Category]]) -> None: def _add_feature_unigrams(self, dataset: t.Iterator[tuple[TokenBag, Category]]) -> None:
""" """

6
unimore_bda_6/analysis/tf_text.py
View file

@ -71,7 +71,7 @@ class TensorflowSentimentAnalyzer(BaseSentimentAnalyzer, metaclass=abc.ABCMeta):
""" """
log.debug("Creating TextVectorization layer...") log.debug("Creating TextVectorization layer...")
layer = tensorflow.keras.layers.TextVectorization( layer = tensorflow.keras.layers.TextVectorization(
standardize=self.tokenizer.tokenize_tensorflow, standardize=self.tokenizer.tokenize_tensorflow_and_expand_dims,
max_tokens=TENSORFLOW_MAX_FEATURES.__wrapped__ max_tokens=TENSORFLOW_MAX_FEATURES.__wrapped__
) )
log.debug("Created TextVectorization layer: %s", layer) log.debug("Created TextVectorization layer: %s", layer)
@ -177,8 +177,8 @@ class TensorflowCategorySentimentAnalyzer(TensorflowSentimentAnalyzer):
dataset_func=dataset_func, dataset_func=dataset_func,
conversion_func=Review.to_tensor_tuple, conversion_func=Review.to_tensor_tuple,
output_signature=( output_signature=(
tensorflow.TensorSpec(shape=(1,), dtype=tensorflow.string, name="text"), tensorflow.TensorSpec(shape=(), dtype=tensorflow.string, name="text"),
tensorflow.TensorSpec(shape=(5,), dtype=tensorflow.float32, name="review_one_hot"), tensorflow.TensorSpec(shape=(1, 5,), dtype=tensorflow.float32, name="review_one_hot"),
), ),
) )